From f97613af86b533f1c466b3da687bdf6961e30252 Mon Sep 17 00:00:00 2001
From: Susumu Sakamoto <susumusakamoto19@gmail.com>
Date: Wed, 29 Sep 2021 00:59:43 +0900
Subject: [PATCH] finish lab

---
 .ipynb_checkpoints/Untitled-checkpoint.ipynb | 576 ++++++++++++++++++-
 Untitled.ipynb                               | 576 ++++++++++++++++++-
 2 files changed, 1132 insertions(+), 20 deletions(-)

diff --git a/.ipynb_checkpoints/Untitled-checkpoint.ipynb b/.ipynb_checkpoints/Untitled-checkpoint.ipynb
index 7b5f0b3..f0e25cd 100644
--- a/.ipynb_checkpoints/Untitled-checkpoint.ipynb
+++ b/.ipynb_checkpoints/Untitled-checkpoint.ipynb
@@ -41,17 +41,53 @@
    ]
   },
   {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "f56d81a7",
+   "cell_type": "markdown",
+   "id": "f1948f30",
    "metadata": {},
-   "outputs": [],
-   "source": []
+   "source": [
+    "#### 1. State the null hypothesis\n",
+    "\n",
+    "Changing the power of the plasma beam has **NO** significant effect on the etching rate by the machine."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "baf5be91",
+   "metadata": {},
+   "source": [
+    "#### 2. State the alternate hypothesis\n",
+    "\n",
+    "At least one change of the plasma beam power **has significant effect** on the etching rate by the machine."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "6c924dae",
+   "metadata": {},
+   "source": [
+    "#### 3. What is the significance level\n",
+    "\n",
+    "Significance level = 0.05"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "8c4a2b63",
+   "metadata": {},
+   "source": [
+    "#### 4. What are the degrees of freedom of model, error terms, and total DoF\n",
+    "\n",
+    "Degree of freedom of the model = 4. (each watts has 5 data set, so 5 - 1)\n",
+    "\n",
+    "error terms = i don't really know how to get this\n",
+    "\n",
+    "total DoF = 14 (total data is 15)"
+   ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "a891a030",
+   "id": "f5b616c7",
    "metadata": {},
    "outputs": [],
    "source": []
@@ -69,18 +105,538 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 38,
    "id": "f182b9b4",
    "metadata": {},
    "outputs": [],
+   "source": [
+    "import numpy as np\n",
+    "import pandas as pd\n",
+    "import statsmodels.api as sm\n",
+    "from statsmodels.formula.api import ols"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 39,
+   "id": "65cd134c",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>Power</th>\n",
+       "      <th>Etching Rate</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>160 W</td>\n",
+       "      <td>5.43</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>180 W</td>\n",
+       "      <td>6.24</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>200 W</td>\n",
+       "      <td>8.79</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>160 W</td>\n",
+       "      <td>5.71</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>180 W</td>\n",
+       "      <td>6.71</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>5</th>\n",
+       "      <td>200 W</td>\n",
+       "      <td>9.20</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>6</th>\n",
+       "      <td>160 W</td>\n",
+       "      <td>6.22</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>7</th>\n",
+       "      <td>180 W</td>\n",
+       "      <td>5.98</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>8</th>\n",
+       "      <td>200 W</td>\n",
+       "      <td>7.90</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9</th>\n",
+       "      <td>160 W</td>\n",
+       "      <td>6.01</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>10</th>\n",
+       "      <td>180 W</td>\n",
+       "      <td>5.66</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>11</th>\n",
+       "      <td>200 W</td>\n",
+       "      <td>8.15</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>12</th>\n",
+       "      <td>160 W</td>\n",
+       "      <td>5.59</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>13</th>\n",
+       "      <td>180 W</td>\n",
+       "      <td>6.60</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>14</th>\n",
+       "      <td>200 W</td>\n",
+       "      <td>7.55</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "   Power   Etching Rate\n",
+       "0   160 W          5.43\n",
+       "1   180 W          6.24\n",
+       "2   200 W          8.79\n",
+       "3   160 W          5.71\n",
+       "4   180 W          6.71\n",
+       "5   200 W          9.20\n",
+       "6   160 W          6.22\n",
+       "7   180 W          5.98\n",
+       "8   200 W          7.90\n",
+       "9   160 W          6.01\n",
+       "10  180 W          5.66\n",
+       "11  200 W          8.15\n",
+       "12  160 W          5.59\n",
+       "13  180 W          6.60\n",
+       "14  200 W          7.55"
+      ]
+     },
+     "execution_count": 39,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "data = pd.read_excel('files_for_lab/anova_lab_data.xlsx')\n",
+    "data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 40,
+   "id": "d8a62b83",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>Etching Rate</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>count</th>\n",
+       "      <td>15.000000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>mean</th>\n",
+       "      <td>6.782667</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>std</th>\n",
+       "      <td>1.228643</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>min</th>\n",
+       "      <td>5.430000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>25%</th>\n",
+       "      <td>5.845000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>50%</th>\n",
+       "      <td>6.240000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>75%</th>\n",
+       "      <td>7.725000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>max</th>\n",
+       "      <td>9.200000</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "       Etching Rate\n",
+       "count     15.000000\n",
+       "mean       6.782667\n",
+       "std        1.228643\n",
+       "min        5.430000\n",
+       "25%        5.845000\n",
+       "50%        6.240000\n",
+       "75%        7.725000\n",
+       "max        9.200000"
+      ]
+     },
+     "execution_count": 40,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "data.describe()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 41,
+   "id": "90e09d58",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Index(['Power ', 'Etching Rate'], dtype='object')"
+      ]
+     },
+     "execution_count": 41,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "data.columns"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 42,
+   "id": "29424a6b",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "160 W    5\n",
+       "200 W    5\n",
+       "180 W    5\n",
+       "Name: Power , dtype: int64"
+      ]
+     },
+     "execution_count": 42,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "data['Power '].value_counts()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 43,
+   "id": "aaa54da8",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>Etching Rate</th>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>Power</th>\n",
+       "      <th></th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>160 W</th>\n",
+       "      <td>5.792</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>180 W</th>\n",
+       "      <td>6.238</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>200 W</th>\n",
+       "      <td>8.318</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "        Etching Rate\n",
+       "Power               \n",
+       "160 W          5.792\n",
+       "180 W          6.238\n",
+       "200 W          8.318"
+      ]
+     },
+     "execution_count": 43,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "data.groupby('Power ').agg(np.mean)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "id": "2d6a459e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "new_col = []\n",
+    "for col in data.columns:\n",
+    "    new_col.append(col.replace(' ','_'))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 29,
+   "id": "5b886155",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Index(['Power_', 'Etching_Rate'], dtype='object')"
+      ]
+     },
+     "execution_count": 29,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "data.columns = new_col\n",
+    "data.columns"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 31,
+   "id": "883b070f",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>df</th>\n",
+       "      <th>sum_sq</th>\n",
+       "      <th>mean_sq</th>\n",
+       "      <th>F</th>\n",
+       "      <th>PR(&gt;F)</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>C(Power_)</th>\n",
+       "      <td>2.0</td>\n",
+       "      <td>18.176653</td>\n",
+       "      <td>9.088327</td>\n",
+       "      <td>36.878955</td>\n",
+       "      <td>0.000008</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>Residual</th>\n",
+       "      <td>12.0</td>\n",
+       "      <td>2.957240</td>\n",
+       "      <td>0.246437</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "             df     sum_sq   mean_sq          F    PR(>F)\n",
+       "C(Power_)   2.0  18.176653  9.088327  36.878955  0.000008\n",
+       "Residual   12.0   2.957240  0.246437        NaN       NaN"
+      ]
+     },
+     "execution_count": 31,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "import statsmodels.api as sm\n",
+    "from statsmodels.formula.api import ols\n",
+    "\n",
+    "model = ols('Etching_Rate ~ C(Power_)',data=data).fit()\n",
+    "sm.stats.anova_lm(model)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "b2e8ecde",
+   "metadata": {},
+   "source": [
+    "p-value(0.000008) is less than significant level (0.05), so the null hypothesis is rejected.\n",
+    "\n",
+    "There is at least one significant difference between the powers."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "782e50ff",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "0f07b069",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "fb4f3f52",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "88069bc5",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "27e00963",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "03805c46",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "4338ed14",
+   "metadata": {},
+   "outputs": [],
    "source": []
   }
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "ironhack",
+   "display_name": "Python 3",
    "language": "python",
-   "name": "ironhack"
+   "name": "python3"
   },
   "language_info": {
    "codemirror_mode": {
@@ -92,7 +648,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.8.5"
+   "version": "3.8.8"
   }
  },
  "nbformat": 4,
diff --git a/Untitled.ipynb b/Untitled.ipynb
index 7b5f0b3..f0e25cd 100644
--- a/Untitled.ipynb
+++ b/Untitled.ipynb
@@ -41,17 +41,53 @@
    ]
   },
   {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "f56d81a7",
+   "cell_type": "markdown",
+   "id": "f1948f30",
    "metadata": {},
-   "outputs": [],
-   "source": []
+   "source": [
+    "#### 1. State the null hypothesis\n",
+    "\n",
+    "Changing the power of the plasma beam has **NO** significant effect on the etching rate by the machine."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "baf5be91",
+   "metadata": {},
+   "source": [
+    "#### 2. State the alternate hypothesis\n",
+    "\n",
+    "At least one change of the plasma beam power **has significant effect** on the etching rate by the machine."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "6c924dae",
+   "metadata": {},
+   "source": [
+    "#### 3. What is the significance level\n",
+    "\n",
+    "Significance level = 0.05"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "8c4a2b63",
+   "metadata": {},
+   "source": [
+    "#### 4. What are the degrees of freedom of model, error terms, and total DoF\n",
+    "\n",
+    "Degree of freedom of the model = 4. (each watts has 5 data set, so 5 - 1)\n",
+    "\n",
+    "error terms = i don't really know how to get this\n",
+    "\n",
+    "total DoF = 14 (total data is 15)"
+   ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "a891a030",
+   "id": "f5b616c7",
    "metadata": {},
    "outputs": [],
    "source": []
@@ -69,18 +105,538 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 38,
    "id": "f182b9b4",
    "metadata": {},
    "outputs": [],
+   "source": [
+    "import numpy as np\n",
+    "import pandas as pd\n",
+    "import statsmodels.api as sm\n",
+    "from statsmodels.formula.api import ols"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 39,
+   "id": "65cd134c",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>Power</th>\n",
+       "      <th>Etching Rate</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>160 W</td>\n",
+       "      <td>5.43</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>180 W</td>\n",
+       "      <td>6.24</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>200 W</td>\n",
+       "      <td>8.79</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>160 W</td>\n",
+       "      <td>5.71</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>180 W</td>\n",
+       "      <td>6.71</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>5</th>\n",
+       "      <td>200 W</td>\n",
+       "      <td>9.20</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>6</th>\n",
+       "      <td>160 W</td>\n",
+       "      <td>6.22</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>7</th>\n",
+       "      <td>180 W</td>\n",
+       "      <td>5.98</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>8</th>\n",
+       "      <td>200 W</td>\n",
+       "      <td>7.90</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9</th>\n",
+       "      <td>160 W</td>\n",
+       "      <td>6.01</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>10</th>\n",
+       "      <td>180 W</td>\n",
+       "      <td>5.66</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>11</th>\n",
+       "      <td>200 W</td>\n",
+       "      <td>8.15</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>12</th>\n",
+       "      <td>160 W</td>\n",
+       "      <td>5.59</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>13</th>\n",
+       "      <td>180 W</td>\n",
+       "      <td>6.60</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>14</th>\n",
+       "      <td>200 W</td>\n",
+       "      <td>7.55</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "   Power   Etching Rate\n",
+       "0   160 W          5.43\n",
+       "1   180 W          6.24\n",
+       "2   200 W          8.79\n",
+       "3   160 W          5.71\n",
+       "4   180 W          6.71\n",
+       "5   200 W          9.20\n",
+       "6   160 W          6.22\n",
+       "7   180 W          5.98\n",
+       "8   200 W          7.90\n",
+       "9   160 W          6.01\n",
+       "10  180 W          5.66\n",
+       "11  200 W          8.15\n",
+       "12  160 W          5.59\n",
+       "13  180 W          6.60\n",
+       "14  200 W          7.55"
+      ]
+     },
+     "execution_count": 39,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "data = pd.read_excel('files_for_lab/anova_lab_data.xlsx')\n",
+    "data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 40,
+   "id": "d8a62b83",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>Etching Rate</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>count</th>\n",
+       "      <td>15.000000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>mean</th>\n",
+       "      <td>6.782667</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>std</th>\n",
+       "      <td>1.228643</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>min</th>\n",
+       "      <td>5.430000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>25%</th>\n",
+       "      <td>5.845000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>50%</th>\n",
+       "      <td>6.240000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>75%</th>\n",
+       "      <td>7.725000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>max</th>\n",
+       "      <td>9.200000</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "       Etching Rate\n",
+       "count     15.000000\n",
+       "mean       6.782667\n",
+       "std        1.228643\n",
+       "min        5.430000\n",
+       "25%        5.845000\n",
+       "50%        6.240000\n",
+       "75%        7.725000\n",
+       "max        9.200000"
+      ]
+     },
+     "execution_count": 40,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "data.describe()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 41,
+   "id": "90e09d58",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Index(['Power ', 'Etching Rate'], dtype='object')"
+      ]
+     },
+     "execution_count": 41,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "data.columns"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 42,
+   "id": "29424a6b",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "160 W    5\n",
+       "200 W    5\n",
+       "180 W    5\n",
+       "Name: Power , dtype: int64"
+      ]
+     },
+     "execution_count": 42,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "data['Power '].value_counts()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 43,
+   "id": "aaa54da8",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>Etching Rate</th>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>Power</th>\n",
+       "      <th></th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>160 W</th>\n",
+       "      <td>5.792</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>180 W</th>\n",
+       "      <td>6.238</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>200 W</th>\n",
+       "      <td>8.318</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "        Etching Rate\n",
+       "Power               \n",
+       "160 W          5.792\n",
+       "180 W          6.238\n",
+       "200 W          8.318"
+      ]
+     },
+     "execution_count": 43,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "data.groupby('Power ').agg(np.mean)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "id": "2d6a459e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "new_col = []\n",
+    "for col in data.columns:\n",
+    "    new_col.append(col.replace(' ','_'))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 29,
+   "id": "5b886155",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Index(['Power_', 'Etching_Rate'], dtype='object')"
+      ]
+     },
+     "execution_count": 29,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "data.columns = new_col\n",
+    "data.columns"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 31,
+   "id": "883b070f",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>df</th>\n",
+       "      <th>sum_sq</th>\n",
+       "      <th>mean_sq</th>\n",
+       "      <th>F</th>\n",
+       "      <th>PR(&gt;F)</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>C(Power_)</th>\n",
+       "      <td>2.0</td>\n",
+       "      <td>18.176653</td>\n",
+       "      <td>9.088327</td>\n",
+       "      <td>36.878955</td>\n",
+       "      <td>0.000008</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>Residual</th>\n",
+       "      <td>12.0</td>\n",
+       "      <td>2.957240</td>\n",
+       "      <td>0.246437</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "             df     sum_sq   mean_sq          F    PR(>F)\n",
+       "C(Power_)   2.0  18.176653  9.088327  36.878955  0.000008\n",
+       "Residual   12.0   2.957240  0.246437        NaN       NaN"
+      ]
+     },
+     "execution_count": 31,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "import statsmodels.api as sm\n",
+    "from statsmodels.formula.api import ols\n",
+    "\n",
+    "model = ols('Etching_Rate ~ C(Power_)',data=data).fit()\n",
+    "sm.stats.anova_lm(model)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "b2e8ecde",
+   "metadata": {},
+   "source": [
+    "p-value(0.000008) is less than significant level (0.05), so the null hypothesis is rejected.\n",
+    "\n",
+    "There is at least one significant difference between the powers."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "782e50ff",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "0f07b069",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "fb4f3f52",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "88069bc5",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "27e00963",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "03805c46",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "4338ed14",
+   "metadata": {},
+   "outputs": [],
    "source": []
   }
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "ironhack",
+   "display_name": "Python 3",
    "language": "python",
-   "name": "ironhack"
+   "name": "python3"
   },
   "language_info": {
    "codemirror_mode": {
@@ -92,7 +648,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.8.5"
+   "version": "3.8.8"
   }
  },
  "nbformat": 4,